MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the idempotentHint annotation, the description adds meaningful behavioral context: session-only tokens expire versus permanent config tokens, and no-args invocation returns a login link. It does not disclose error cases or security storage details, but for an auth tool with sparse annotations, it provides valuable added transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is informative but somewhat run-on and informally structured, mixing context, configuration steps, and call instructions into a dense paragraph. It front-loads the main purpose and each sentence adds value, but it could be reorganized into clearer guidance for the two invocation modes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter auth tool with no output schema, the description covers the key modes of use, the permanent versus session distinction, and the no-args behavior. It does not detail response shapes or errors, but the provided context is sufficient for an agent to select and invoke the tool correctly in common scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has zero description coverage, so the description must compensate. It does so by explaining that the optional 'token' parameter expects a JWT pasted by the user, and that omitting it triggers the browser-link flow. This gives the parameter practical meaning beyond the bare string type in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool authenticates an MCP.AI connection for IDE agents via browser login and access token. It distinguishes the tool's purpose by explaining both the config-based and session-based authentication flows, though it does not explicitly contrast with the sibling 'connect' tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: it explains the recommended permanent configuration approach, the alternative session-only token paste, and the no-args behavior to retrieve the login link. It lacks explicit when-not-to-use or alternatives compared to sibling tools like 'connect', but the guidance is actionable and specific.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The six platform tools (connect, marketplace, report_bug, etc.) are clearly distinct, and the two TCU tools have separate purposes: one lists recent acórdãos without a keyword, the other performs keyword searches. However, authenticate and connect both deal with credentials/status, which could cause minor confusion, and tcu_acordaos_recentes vs tcu_buscar overlap partially since both return TCU content. Overall, boundaries are clear with only slight ambiguity.
Naming is inconsistent: TCU-specific tools use snake_case with a 'tcu_' prefix (tcu_buscar, tcu_acordaos_recentes), while platform tools use camelCase or simple lowercase (authenticate, connect, marketplace, report_bug, show_version, toolkit_info). No consistent verb/noun pattern or style across the set.
The total of 8 tools is within a reasonable range, but only 2 are TCU-specific; the other 6 are generic platform utilities. For a server titled 'TCU Jurisprudência', the count feels off—either too many unrelated tools or too few domain tools. It's borderline, not egregious.
The TCU domain is covered by a search and a recent-list tool, but lacks operations like fetching a specific acórdão by ID, filtering by date/relator, or browsing related jurisprudência. The platform tools cover their own generic concerns, but the domain surface feels minimal—no obvious dead ends, but notable gaps exist for a jurisprudence-focused server.